JMIR Publications

ABSTRACT

Background:

In epidemiological studies, finding the best subset of factors is challenging when the number of explanatory variables is large.

Objective:

Our study has two aims: first, to identify essential depression-associated factors using XGBoost machine-learning algorithm from a big survey data, the Korea National Health and Nutrition Examination Survey, 2012–2016; Second, to achieve a comprehensive understanding of multifactorial feature in depression using network analysis.

Methods:

An XGBoost model was trained and tested to classify “current depression” and “no lifetime depression” for a dataset of 120 variables for 12,596 cases. The optimal XGBoost hyperparameters were set by an automated machine learning tool (TPOT), and a high-performance sparse model was obtained by feature selection using the feature importance value of XGBoost. We performed statistical tests on the model and non-model factors using survey-weighted multiple logistic regression and drew a correlation network among factors. We also took statistical tests for the confounder or interaction effect of selected risk factors when it was suspected on the network.

Results:

The XGBoost-derived depression model consisted of 18 factors with a 0.86 area under the weighted receiver operating characteristic curves. Two non-model factors could be found using the model factors, and the factors were classified into direct (P < 0.05) or indirect (P >= 0.05) according to their statistical significance of association with depression. Perceived stress and asthma were the most remarkable risk factors, and urine specific gravity was a novel protective factor. The depression-factor network showed clusters of socioeconomic status and quality-of-life factors and suggested that educational level and sex might be predisposing factors. Indirect factors (eg, diabetes, hypercholesterolemia, smoking) were involved in confounding or interaction effects of direct factors: triglyceride level was a confounder of hypercholesterolemia and diabetes; smoking had a significant risk in females; weight gain happened in depression with diabetes.

Conclusions:

XGBoost and network analysis were useful to discover depression-related factors and their relationships and can be applied to epidemiologic studies using big survey data.